Azure ChatGPT: Private and secure ChatGPT for internal enterprise use

Re:Azure ChatGPT: Private and secure ChatGPT for internal en... by dr_dshiv on Monday August 14, 2023 @01:49AM (#37117888)

IMO Llama2 really isn’t close to 3.5. It still has regular mode collapse (or whatever you call getting repetitive and nonsensical responses after a while), it has very poor mathematical/logical reasoning and is not good at following multi-part instructions.

It just sounds like 3.5/4 because it was trained on it.

[ Parent | on HN ]

Re:Azure ChatGPT: Private and secure ChatGPT for internal en... by geysersam on Monday August 14, 2023 @02:58AM (#37118252)

You're mixing up the language model with the chat bot.

The llama2 is a language model. I imagine the language model behind chatgpt is not much different (perhaps it's better, but not by many months AI research time). It likely also suffers from "mode collapse" issues etc.

But 3.5 also has a lot of systems around it that detects mode collapse and applies some kind of mitigation, forcing the model to give a more reasonable output. Mathematical / logical reasoning questions are likely also detected hand passed on in some form to a separate system.

[ Parent | on HN ]

Re:Azure ChatGPT: Private and secure ChatGPT for internal en... by dr_dshiv on Monday August 14, 2023 @09:18AM (#37120707)

So this would be testable by showing that chatGPT makes more mistakes than prompting via API? Or would you consider the API a chatbot, too?

[ Parent | on HN ]

Re:Azure ChatGPT: Private and secure ChatGPT for internal en... by geysersam on Monday August 14, 2023 @09:26AM (#37120791)

I don't think there's any public interface to the LLM underlying ChatGPT, so the only ones able to test this are openAI engineers.

[ Parent | on HN ]

Re:Azure ChatGPT: Private and secure ChatGPT for internal en... by vorticalbox on Monday August 14, 2023 @03:58AM (#37118550)

This is what presence_penalty and frequency_penalty are for.

[ Parent | on HN ]

Re:Azure ChatGPT: Private and secure ChatGPT for internal en... by nl on Monday August 14, 2023 @03:59AM (#37118552)

Llama 2 wasn't trained on ChatGPT/GPT4. I think maybe you are thinking of the Vicuna models?

https://lmsys.org/blog/2023-03-30-vicuna/

[ Parent | on HN ]

Re:Azure ChatGPT: Private and secure ChatGPT for internal en... by dr_dshiv on Monday August 14, 2023 @09:20AM (#37120730)

So it’s true that it would violate the OpenAI terms for Llama to be trained with ChatGPT completions, but how do we know? We don’t know the training data for Llama, we just get weights.

[ Parent | on HN ]

Re:Azure ChatGPT: Private and secure ChatGPT for internal en... by nl on Tuesday August 15, 2023 @01:53AM (#37130683)

The Llama2 paper describes the training data in some detail.

[ Parent | on HN ]